© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85416
    Prev
    Next
    INDEX
    Explanations

    Cartier, Woodson, Charles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     INTERRUPTION
    0.66
    h
    0.66
     Traditions
    0.64
    )
    0.61
     Gloucester
    0.61
     있는
    0.60
    jelasan
    0.59
     Andal
    0.59
     campionato
    0.59
    рили
    0.58
    POSITIVE LOGITS
     be
    0.82
    ts
    0.79
    t
    0.76
    ad
    0.73
    an
    0.69
    ר
    0.68
    р
    0.67
    at
    0.66
    ps
    0.66
    ي
    0.64
    Activations Density 0.000%

    No Known Activations